# Import pandas
import pandas as pd

# Import datasets
hiv = pd.read_csv(r"C:\Users\Lyz\Documents\Python\Portfolio\HIV_AIDS\HIV.csv")
aids = pd.read_csv(r"C:\Users\Lyz\Documents\Python\Portfolio\HIV_AIDS\AIDS.csv")
death = pd.read_csv(r"C:\Users\Lyz\Documents\Python\Portfolio\HIV_AIDS\Death.csv")

# Merge dataframes
df = pd.merge(hiv, aids, on = ["County", "Year"])
HIV_AIDS = pd.merge(df, death, on = ["County", "Year"])

# Print the full list of columns
print(list(HIV_AIDS.columns))

['Year', 'County', 'HIV_Count', 'HIV_Denom', 'HIV_Rate', 'HIV_MOV', 'AIDS_Count', 'AIDS_Denom', 'AIDS_Rate', 'AIDS_MOV', 'Death_Count', 'Death_Rate']

HIV_AIDS.head(20)
# drop Florida as this is not a county but a state
state = ["Florida"]
HIV_AIDS = HIV_AIDS[HIV_AIDS.County.isin(state) == False]
# sort data ascending by year
HIV_AIDS = HIV_AIDS.sort_values("Year")

HIV_AIDS.head(5)

	Year	County	HIV_Count	HIV_Denom	HIV_Rate	HIV_MOV	AIDS_Count	AIDS_Denom	AIDS_Rate	AIDS_MOV	Death_Count	Death_Rate
649	2012	Washington	1	24,921	4.0	NaN	3	24921.0	12.0	NaN	0	0.0
614	2012	Holmes	2	19,997	10.0	NaN	2	19997.0	10.0	NaN	0	0.0
613	2012	Hillsborough	273	1,260,887	21.7	2.6	196	1260887.0	15.5	2.2	57	4.4
612	2012	Highlands	4	98,980	4.0	NaN	4	98980.0	4.0	NaN	5	4.7
611	2012	Hernando	7	173,214	4.0	3.0	9	173214.0	5.2	3.4	4	1.9

import plotly.graph_objects as go

fig = go.Figure()
fig.add_trace(go.Bar(
    x = HIV_AIDS["County"],
    y = HIV_AIDS["HIV_Rate"],
    name = "HIV Rate",
    marker_color = 'indianred'
))
fig.add_trace(go.Bar(
    x = HIV_AIDS["County"],
    y = HIV_AIDS["AIDS_Rate"],
    name = "AIDs Rate",
    marker_color = 'lightsalmon'
))
fig.add_trace(go.Bar(
    x = HIV_AIDS["County"],
    y = HIV_AIDS["Death_Rate"],
    name = "Death Rate",
    marker_color = 'lightsalmon'
))


fig.update_layout(barmode = "group", xaxis_tickangle=-45)
fig.show()
# With this code, we can't visualize by year

import plotly.graph_objects as go
import pandas as pd

# Extract only the year part from the 'Year' column
HIV_AIDS['Year'] = HIV_AIDS['Year'].astype(str)
HIV_AIDS['Year'] = HIV_AIDS['Year'].str.extract('(\d{4})', expand=False)
HIV_AIDS['Year'] = HIV_AIDS['Year'].astype(int)
HIV_AIDS['Year'] = pd.to_datetime(HIV_AIDS['Year'], format='%Y')
years = sorted(HIV_AIDS['Year'].dt.year.unique())

# Create a function to filter data by year
def filter_data_by_year(data, year):
    return data[data['Year'].dt.year == year]

# Create a slider
steps = []
for year in years:
    filtered_data = filter_data_by_year(HIV_AIDS, year)
    step = dict(
        method="restyle",
        args=[{"x": [filtered_data["County"]], 
               "y": [filtered_data["HIV_Rate"], filtered_data["AIDS_Rate"], filtered_data["Death_Rate"]]}],
        label=str(year)
    )
    steps.append(step)

slider = dict(
    active=0,
    currentvalue={"prefix": "Year: "},
    pad={"t": 50},
    steps=steps
)

# Initial data for the first year
initial_data = filter_data_by_year(HIV_AIDS, years[0])

fig = go.Figure()

fig.add_trace(go.Bar(
    x=initial_data["County"],
    y=initial_data["HIV_Rate"],
    name="HIV Rate",
    marker_color='blue'
))
fig.add_trace(go.Bar(
    x=initial_data["County"],
    y=initial_data["AIDS_Rate"],
    name="AIDs Rate",
    marker_color='mediumaquamarine'
))
fig.add_trace(go.Bar(
    x=initial_data["County"],
    y=initial_data["Death_Rate"],
    name="Death Rate",
    marker_color='green'
))

# Update the layout
fig.update_layout(
    barmode="group",
    xaxis_tickangle=-45,
    sliders=[slider]
)

fig.show()